Exploring nonlinear feature space dimension reduction and data representation in breast CADx with Laplacian eigenmaps and ‐SNE

Abstract

In this preliminary study, recently developed unsupervised nonlinear dimension reduction (DR) and data representation techniques were applied to computer‐extracted breast lesion feature spaces across three separate imaging modalities: Ultrasound (U.S.) with 1126 cases, dynamic contrast enhanced magnetic resonance imaging with 356 cases, and full‐field digital mammography with 245 cases. Two methods for nonlinear DR were explored: Laplacian eigenmaps [M. Belkin and P. Niyogi, “Laplacian eigenmaps for dimensionality reduction and data representation,” Neural Comput. 15, 1373–1396 (2003)] and ‐distributed stochastic neighbor embedding (‐SNE) [L. van der Maaten and G. Hinton, “Visualizing data using t‐SNE,” J. Mach. Learn. Res. 9, 2579–2605 (2008)].

Document Details

Document Type
Pub Defense Publication
Publication Date
Dec 22, 2009
Source ID
10.1118/1.3267037

Entities

People

  • Andrew R. Jamieson
  • Hui Li
  • Karen Drukker
  • Maryellen Lissak Giger
  • Neha Bhooshan
  • Yading Yuan

Organizations

  • National Institutes of Health
  • United States Department of Defense
  • United States Department of Energy

Tags

Readers

  • Computer Vision.
  • Neural Network Machine Learning.
  • Oncology and Biomarker-Based Cancer Detection.

Technology Areas

  • Space